n-Gram based Language Separation for Minority Languages

Attachement for publication n-Gram based Language Separation for Minority Languages (to appear). Contains scripts and evaluation results. If allowed, document will be added here as new version after publication. Else URL to document will be added. The scripts are specialized for this study and – especially since they rely on a specific setup – should not be considered as generically applicable but merely as documentation for the evaluation. Since the described analysis is using very basic text mining concepts, it is more recommendable to reimplement the algorithm for specific scenarios. Reproduce python3 _spoznajrec.py 3 python3 _zelenjerec.py 3